Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 85784
    Prev
    Next
    INDEX
    Explanations

    references to England and its regions, especially Wales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    country England

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disponibilités
    -0.71
    contentLoaded
    -0.65
    httphttps
    -0.62
    Datuak
    -0.56
    principalColumn
    -0.56
     iprot
    -0.55
    ">)</
    -0.55
    astéroïdes
    -0.55
    ieteur
    -0.55
    ▻
    -0.54
    POSITIVE LOGITS
     England
    1.07
    England
    0.99
    england
    0.85
     england
    0.82
     ENGLAND
    0.81
    Angleterre
    0.67
     Angleterre
    0.67
     Engl
    0.66
     Inglaterra
    0.66
     English
    0.65
    Activations Density 0.006%

    No Known Activations